4 papers
Bridging AI and Clinical Reasoning: Abductive Explanations for Alignment on Critical Symptoms
Belona Sonna, Alban Grastien
Artificial intelligence (AI) has demonstrated strong potential in clinical diagnostics, often achieving accuracy comparable to or exceeding that of human experts. A key challenge,…
Formal Abductive Explanations for Navigating Mental Health Help-Seeking and Diversity in Tech Workplaces
Belona Sonna, Alain Momo, Alban Grastien
This work proposes a formal abductive explanation framework designed to systematically uncover rationales underlying AI predictions of mental health help-seeking within tech workpl…
Beyond Verification: Abductive Explanations for Post-AI Assessment of Privacy Leakage
Belona Sonna, Alban Grastien, Claire Benn
Privacy leakage in AI-based decision processes poses significant risks, particularly when sensitive information can be inferred. We propose a formal framework to audit privacy leak…
On Explaining Proxy Discrimination and Unfairness in Individual Decisions Made by AI Systems
Belona Sonna, Alban Grastien
Artificial intelligence (AI) systems in high-stakes domains raise concerns about proxy discrimination, unfairness, and explainability. Existing audits often fail to reveal why unfa…